# Integrating Rules and Semantics for LLM-Based C-to-Rust Translation

arXiv: https://arxiv.org/abs/2508.06926 · HTML: https://mlsanity.com/paper/2508.06926/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2025.

## Built on by (most cited first, 6 of 6)

- [SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents](https://mlsanity.com/paper/2606.28434/) (2026)
- [Adversarial Agent Collaboration for Correctness Improvements of C to Safe Rust Translation](https://mlsanity.com/paper/2510.03879/) (2025)
- [ENCRUST: Encapsulated Substitution and Agentic Refinement on a Live Scaffold for Safe C-to-Rust Translation](https://mlsanity.com/paper/2604.04527/) (2026)
- [ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories](https://mlsanity.com/paper/2604.07341/) (2026)
- [His2Trans: A Knowledge-Guided Agentic Framework for Project-Level C-to-Rust Migration](https://mlsanity.com/paper/2603.02617/) (2026)
- [Translator vs. Challenger: Adversarial Agentic Learning for C-to-Rust Translation](https://mlsanity.com/paper/2609.15381/) (2026)

## Abstract (arXiv)

Automated translation of legacy C code into Rust aims to ensure memory safety while reducing the burden of manual migration. Early approaches in code translation rely on static rule-based methods, but they suffer from limited coverage due to dependence on predefined rule patterns. Recent works regard the task as a sequence-to-sequence problem by leveraging large language models (LLMs). Although these LLM-based methods are capable of reducing unsafe code blocks, the translated code often exhibits issues in following Rust rules and maintaining semantic consistency. On one hand, existing methods adopt a direct prompting strategy to translate the C code, which struggles to accommodate the syntactic rules between C and Rust. On the other hand, this strategy makes it difficult for LLMs to accurately capture the semantics of complex code. To address these challenges, we propose IRENE, an LLM-based framework that Integrates RulEs aNd sEmantics to enhance translation. IRENE consists of three modules: 1) a rule-augmented retrieval module that selects relevant translation examples based on rules generated from a static analyzer developed by us, thereby improving the handling of Rust rules; 2) a structured summarization module that produces a structured summary for guiding LLMs to enhance the semantic understanding of C code; 3) an error-driven translation module that leverages compiler diagnostics to iteratively refine translations. We evaluate IRENE on two datasets (xCodeEval, a public dataset, and HW-Bench, an industrial dataset provided by Huawei) and eight LLMs, focusing on translation accuracy and safety.